arXiv subjects

Stéphane Caron

Publications and source records attributed to Stéphane Caron.

At least 19 recordsLinked to original sources

arXiv2026

LEAP: Learning Emergent Active Perception for Quadruped Navigation

Active perception allows autonomous agents to select their viewpoints rather than passively process the viewpoints given to them, enabling them to target where to reduce uncertainty about their environment. Learned systems typically encourage this behavior with hand-designed proxy objectives, such as coverage or curiosity bonuses, that may conflict with the task. In this work, we propose a method to learn emergent active perception (LEAP) without augmentation of the task objective. We formulate the problem of goal-oriented navigation over hazardous terrains with goals that must be discovered visually. We then propose an architecture for navigation policies with active perception, and train them on a terrain curriculum where task pressure alone leads to the emergence of gaze control. Key to this emergence, LEAP works on a gaze-invariant representation that integrates depth images into egocentric belief maps. We validate its performance in held-out evaluation scenarios, where it achieves a 92.7% success rate, compared to 74.2% for scripted or 34.5% for passive perception, and comes within 4.6 points of a privileged oracle. We validate that LEAP navigation policies, unchanged, can be directly applied to steering quadrupedal locomotion policies in physics simulation.

cs.RO↗

arXiv2026

Koopman DCM: Unstable Eigenfunctions as Data-driven Representations for Legged Balancing

In legged locomotion, divergent components of motion (DCMs) have emerged as characteristic states for balance control. They isolate the unstable mode of the dynamics but, in existing formulations, apply only to reduced models such as the linear inverted pendulum. In this study, we show how DCMs can be more generally formulated as Koopman eigenfunctions. Whereas Koopman analysis typically targets eigenvalues near zero, which capture conserved or slowly varying quantities, our investigation leads us to deliberately search for unstable eigenpairs with large eigenvalues. The resulting Koopman DCMs are data-driven observables trained using only real-robot data. On a real biped, DCMs learned from one hour of robot data improve tracking of reference walking patterns. We further show how learned DCMs provide state-based viability constraints when combined with model predictive control.

cs.RO↗

arXiv2025

Collision avoidance from monocular vision trained with novel view synthesis

Collision avoidance can be checked in explicit environment models such as elevation maps or occupancy grids, yet integrating such models with a locomotion policy requires accurate state estimation. In this work, we consider the question of collision avoidance from an implicit environment model. We use monocular RGB images as inputs and train a collisionavoidance policy from photorealistic images generated by 2D Gaussian splatting. We evaluate the resulting pipeline in realworld experiments under velocity commands that bring the robot on an intercept course with obstacles. Our results suggest that RGB images can be enough to make collision-avoidance decisions, both in the room where training data was collected and in out-of-distribution environments.

cs.RO↗

arXiv2025

A Data-driven Contact Estimation Method for Wheeled-Biped Robots

Contact estimation is a key ability for limbed robots, where making and breaking contacts has a direct impact on state estimation and balance control. Existing approaches typically rely on gate-cycle priors or designated contact sensors. We design a contact estimator that is suitable for the emerging wheeled-biped robot types that do not have these features. To this end, we propose a Bayes filter in which update steps are learned from real-robot torque measurements while prediction steps rely on inertial measurements. We evaluate this approach in extensive real-robot and simulation experiments. Our method achieves better performance while being considerably more sample efficient than a comparable deep-learning baseline.

cs.RO↗

arXiv2021

Stair Climbing Stabilization of the HRP-4 Humanoid Robot using Whole-body Admittance Control

We consider dynamic stair climbing with the HRP-4 humanoid robot as part of an Airbus manufacturing use-case demonstrator. We share experimental knowledge gathered so as to achieve this task, which HRP-4 had never been challenged to before. In particular, we extend walkingstabilization based on linear inverted pendulum tracking by quadratic programming-based wrench distribution and a whole-body admittance controller that applies both end-effector and CoM strategies. While existing stabilizers tend to use either one or the other, our experience suggests that the combination of these two approaches improves tracking performance. We demonstrate this solution in an on-site experiment where HRP-4 climbs an industrial staircase with 18.5 cm high steps, and release our walking controller as open source software.

cs.RO↗

arXiv2021

Humanoid Control Under Interchangeable Fixed and Sliding Unilateral Contacts

In this letter, we propose a whole-body control strategy for humanoid robots in multi-contact settings that enables switching between fixed and sliding contacts under active balance. We compute, in real-time, a safe center-of-mass position and wrench distribution of the contact points based on the Chebyshev center. Our solution is formulated as a quadratic programming problem without a priori computation of balance regions. We assess our approach with experiments highlighting switches between fixed and sliding contact modes in multi-contact configurations. A humanoid robot demonstrates such contact interchanges from fully-fixed to multi-sliding and also shuffling of the foot. The scenarios illustrate the performance of our control scheme in achieving the desired forces, CoM position attractor, and planned trajectories while actively maintaining balance.

cs.RO↗

arXiv2020

Feasible Region: an Actuation-Aware Extension of the Support Region

In legged locomotion the projection of the robot Center of Mass (CoM) being inside the convex hull of the contact points is a commonly accepted sufficient condition to achieve static balancing. However, some of these configurations cannot be realized because the joint torques required to sustain them would be above their limits (actuation limits). In this manuscript we rule out such configurations and define the Feasible Region, a revisited support region that guarantees both global static stability in the sense of tipover and slippage avoidance and of existence of a set of joint-torques that are able to sustain the robot body weight. We show that the feasible region can be employed for the selection of feasible footholds and CoM trajectories to achieve static locomotion on rough terrains, also in presence of load intensive tasks. Key results of our approach include the efficiency in the computation of the feasible region thanks to an Iterative Projection algorithm. This allowed us to carry out successful experiments on the HyQ robot, that was able to negotiate obstacles of moderate dimensions while carrying an extra 10 kg payload.

cs.RO↗

arXiv2020

Biped Stabilization by Linear Feedback of the Variable-Height Inverted Pendulum Model

The variable-height inverted pendulum (VHIP) model enables a new balancing strategy by height variations of the center of mass, in addition to the well-known ankle strategy. We propose a biped stabilizer based on linear feedback of the VHIP that is simple to implement, coincides with the state-of-the-art for small perturbations and is able to recover from larger perturbations thanks to this new strategy. This solution is based on "best-effort" pole placement of a 4D divergent component of motion for the VHIP under input feasibility and state viability constraints. We complement it with a suitable whole-body admittance control law and test the resulting stabilizer on the HRP-4 humanoid robot.

cs.RO↗

arXiv2019

Balance of Humanoid robot in Multi-contact and Sliding Scenarios

This study deals with the balance of humanoid or multi-legged robots in a multi-contact setting where a chosen subset of contacts is undergoing desired sliding-task motions. One method to keep balance is to hold the center-of-mass (CoM) within an admissible convex area. This area should be calculated based on the contact positions and forces. We introduce a methodology to compute this CoM support area (CSA) for multiple fixed and sliding contacts. To select the most appropriate CoM position inside CSA, we account for (i) constraints of multiple fixed and sliding contacts, (ii) desired wrench distribution for contacts, and (iii) desired position of CoM (eventually dictated by other tasks). These are formulated as a quadratic programming optimization problem. We illustrate our approach with pushing against a wall and wiping and conducted experiments using the HRP-4 humanoid robot.

cs.RO↗

arXiv2018

Capturability-based Pattern Generation for Walking with Variable Height

Capturability analysis of the linear inverted pendulum (LIP) model enabled walking with constrained height based on the capture point. We generalize this analysis to the variable-height inverted pendulum (VHIP) and show how it enables 3D walking over uneven terrains based on capture inputs. Thanks to a tailored optimization scheme, we can compute these inputs fast enough for real-time model predictive control. We implement this approach as open-source software and demonstrate it in dynamic simulations.

cs.RO↗

arXiv2018

Balance control using both ZMP and COM height variations: A convex boundedness approach

Developments for 3D control of the center of mass (CoM) of biped robots are currently located in two local minima: on the one hand, methods that allow CoM height variations but only work in the 2D sagittal plane; on the other hand, nonconvex direct transcriptions of centroidal dynamics that are delicate to handle. This paper presents an alternative that controls the CoM in 3D via an indirect transcription that is both low-dimensional and solvable fast enough for real-time control. The key to this development is the notion of boundedness condition, which quantifies the capturability of 3D CoM trajectories.

cs.RO↗

arXiv2017

When to make a step? Tackling the timing problem in multi-contact locomotion by TOPP-MPC

We present a model predictive controller (MPC) for multi-contact locomotion where predictive optimizations are realized by time-optimal path parameterization (TOPP). A key feature of this solution is that, contrary to existing planners where step timings are provided as inputs, here the timing between contact switches is computed as output of a fast nonlinear optimization. This is particularly appealing to multi-contact locomotion, where proper timings depend on terrain topology and suitable heuristics are unknown. We show how to formulate legged locomotion as a TOPP problem and demonstrate the behavior of the resulting TOPP-MPC controller in simulations with a model of the HRP-4 humanoid robot.

cs.RO↗

arXiv2017

Dynamic Walking over Rough Terrains by Nonlinear Predictive Control of the Floating-base Inverted Pendulum

We present a real-time pattern generator for dynamic walking over rough terrains. Our method automatically finds step durations, a critical issue over rough terrains where they depend on terrain topology. To achieve this level of generality, we consider a Floating-base Inverted Pendulum (FIP) model where the center of mass can translate freely and the zero-tilting moment point is allowed to leave the contact surface. This model is equivalent to a linear inverted pendulum with variable center-of-mass height, but its equations of motion remain linear. Our solution then follows three steps: (i) we characterize the FIP contact-stability condition; (ii) we compute feedforward controls by solving a nonlinear optimization over receding-horizon FIP trajectories. Despite running at 30 Hz in a model-predictive fashion, simulations show that the latter is too slow to stabilize dynamic motions. To remedy this, we (iii) linearize FIP feedback control into a constrained linear-quadratic regulator that runs at 300 Hz. We finally demonstrate our solution in simulations with a model of the HRP-4 humanoid robot, including noise and delays over state estimation and foot force control.

cs.RO↗

arXiv2016

Multi-contact Walking Pattern Generation based on Model Preview Control of 3D COM Accelerations

We present a multi-contact walking pattern generator based on preview-control of the 3D acceleration of the center of mass (COM). A key point in the design of our algorithm is the calculation of contact-stability constraints. Thanks to a mathematical observation on the algebraic nature of the frictional wrench cone, we show that the 3D volume of feasible COM accelerations is a always a downward-pointing cone. We reduce its computation to a convex hull of (dual) 2D points, for which optimal O(n log n) algorithms are readily available. This reformulation brings a significant speedup compared to previous methods, which allows us to compute time-varying contact-stability criteria fast enough for the control loop. Next, we propose a conservative trajectory-wide contact-stability criterion, which can be derived from COM-acceleration volumes at marginal cost and directly applied in a model-predictive controller. We finally implement this pipeline and exemplify it with the HRP-4 humanoid model in multi-contact dynamically walking scenarios.

cs.RO↗

arXiv2016

Admissible Velocity Propagation : Beyond Quasi-Static Path Planning for High-Dimensional Robots

Path-velocity decomposition is an intuitive yet powerful approach to address the complexity of kinodynamic motion planning. The difficult trajectory planning problem is solved in two separate, simpler, steps: first, find a path in the configuration space that satisfies the geometric constraints (path planning), and second, find a time-parameterization of that path satisfying the kinodynamic constraints. A fundamental requirement is that the path found in the first step should be time-parameterizable. Most existing works fulfill this requirement by enforcing quasi-static constraints in the path planning step, resulting in an important loss in completeness. We propose a method that enables path-velocity decomposition to discover truly dynamic motions, i.e. motions that are not quasi-statically executable. At the heart of the proposed method is a new algorithm -- Admissible Velocity Propagation -- which, given a path and an interval of reachable velocities at the beginning of that path, computes exactly and efficiently the interval of all the velocities the system can reach after traversing the path while respecting the system kinodynamic constraints. Combining this algorithm with usual sampling-based planners then gives rise to a family of new trajectory planners that can appropriately handle kinodynamic constraints while retaining the advantages associated with path-velocity decomposition. We demonstrate the efficiency of the proposed method on some difficult kinodynamic planning problems, where, in particular, quasi-static methods are guaranteed to fail.

cs.RO↗

arXiv2016

ZMP support areas for multi-contact mobility under frictional constraints

We propose a method for checking and enforcing multi-contact stability based on the Zero-tilting Moment Point (ZMP). The key to our development is the generalization of ZMP support areas to take into account (a) frictional constraints and (b) multiple non-coplanar contacts. We introduce and investigate two kinds of ZMP support areas. First, we characterize and provide a fast geometric construction for the support area generated by valid contact forces, with no other constraint on the robot motion. We call this set the full support area. Next, we consider the control of humanoid robots using the Linear Pendulum Mode (LPM). We observe that the constraints stemming from the LPM induce a shrinking of the support area, even for walking on horizontal floors. We propose an algorithm to compute the new area, which we call pendular support area. We show that, in the LPM, having the ZMP in the pendular support area is a necessary and sufficient condition for contact stability. Based on these developments, we implement a whole-body controller and generate feasible multi-contact motions where an HRP-4 humanoid locomotes in challenging multi-contact scenarios.

cs.RO↗

arXiv2015

Completeness of Randomized Kinodynamic Planners with State-based Steering

Probabilistic completeness is an important property in motion planning. Although it has been established with clear assumptions for geometric planners, the panorama of completeness results for kinodynamic planners is still incomplete, as most existing proofs rely on strong assumptions that are difficult, if not impossible, to verify on practical systems. In this paper, we focus on an important class of kinodynamic planners, namely those that interpolate trajectories in the state space. We provide a proof of probabilistic completeness for these planners under assumptions that can be readily verified from the system's equations of motion and the user-defined interpolation function. Our proof relies crucially on a property of interpolated trajectories, termed second-order continuity (SOC), which we show is tightly related to the ability of a planner to benefit from denser sampling. We analyze the impact of this property in simulations on a low-torque pendulum. Our results show that a simple RRT using a second-order continuous interpolation swiftly finds solution, while it is impossible for the same planner using standard Bezier curves (which are not SOC) to find any solution.

cs.RO↗

arXiv2015

Stability of Surface Contacts for Humanoid Robots: Closed-Form Formulae of the Contact Wrench Cone for Rectangular Support Areas

Humanoid robots locomote by making and breaking contacts with their environment. A crucial problem is therefore to find precise criteria for a given contact to remain stable or to break. For rigid surface contacts, the most general criterion is the Contact Wrench Condition (CWC). To check whether a motion satisfies the CWC, existing approaches take into account a large number of individual contact forces (for instance, one at each vertex of the support polygon), which is computationally costly and prevents the use of efficient inverse-dynamics methods. Here we argue that the CWC can be explicitly computed without reference to individual contact forces, and give closed-form formulae in the case of rectangular surfaces -- which is of practical importance. It turns out that these formulae simply and naturally express three conditions: (i) Coulomb friction on the resultant force, (ii) ZMP inside the support area, and (iii) bounds on the yaw torque. Conditions (i) and (ii) are already known, but condition (iii) is, to the best of our knowledge, novel. It is also of particular interest for biped locomotion, where undesired foot yaw rotations are a known issue. We also show that our formulae yield simpler and faster computations than existing approaches for humanoid motions in single support, and demonstrate their consistency in the OpenHRP simulator.

cs.RO↗